{
  "best_metric": 0.4024839401245117,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 2.435820895522388,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04776119402985075,
      "grad_norm": 0.2979206442832947,
      "learning_rate": 5e-05,
      "loss": 0.551,
      "step": 1
    },
    {
      "epoch": 0.04776119402985075,
      "eval_loss": 0.5565004348754883,
      "eval_runtime": 1.635,
      "eval_samples_per_second": 86.241,
      "eval_steps_per_second": 11.009,
      "step": 1
    },
    {
      "epoch": 0.0955223880597015,
      "grad_norm": 0.35650989413261414,
      "learning_rate": 0.0001,
      "loss": 0.5825,
      "step": 2
    },
    {
      "epoch": 0.14328358208955225,
      "grad_norm": 0.33964836597442627,
      "learning_rate": 9.989294616193017e-05,
      "loss": 0.5787,
      "step": 3
    },
    {
      "epoch": 0.191044776119403,
      "grad_norm": 0.37548384070396423,
      "learning_rate": 9.957224306869053e-05,
      "loss": 0.5376,
      "step": 4
    },
    {
      "epoch": 0.23880597014925373,
      "grad_norm": 0.3570801317691803,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.5277,
      "step": 5
    },
    {
      "epoch": 0.2865671641791045,
      "grad_norm": 0.24230633676052094,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.5205,
      "step": 6
    },
    {
      "epoch": 0.33432835820895523,
      "grad_norm": 0.2895340621471405,
      "learning_rate": 9.73465064747553e-05,
      "loss": 0.5067,
      "step": 7
    },
    {
      "epoch": 0.382089552238806,
      "grad_norm": 0.29996946454048157,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.4935,
      "step": 8
    },
    {
      "epoch": 0.4298507462686567,
      "grad_norm": 0.2953806519508362,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.5314,
      "step": 9
    },
    {
      "epoch": 0.47761194029850745,
      "grad_norm": 0.3664449453353882,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.4517,
      "step": 10
    },
    {
      "epoch": 0.5253731343283582,
      "grad_norm": 0.1971272975206375,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.4932,
      "step": 11
    },
    {
      "epoch": 0.573134328358209,
      "grad_norm": 0.20911331474781036,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.5077,
      "step": 12
    },
    {
      "epoch": 0.6208955223880597,
      "grad_norm": 0.20608961582183838,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.4654,
      "step": 13
    },
    {
      "epoch": 0.6686567164179105,
      "grad_norm": 0.22511093318462372,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.4791,
      "step": 14
    },
    {
      "epoch": 0.7164179104477612,
      "grad_norm": 0.29052355885505676,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.4274,
      "step": 15
    },
    {
      "epoch": 0.764179104477612,
      "grad_norm": 0.16995951533317566,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.4894,
      "step": 16
    },
    {
      "epoch": 0.8119402985074626,
      "grad_norm": 0.19004693627357483,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.4474,
      "step": 17
    },
    {
      "epoch": 0.8597014925373134,
      "grad_norm": 0.20062613487243652,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.4718,
      "step": 18
    },
    {
      "epoch": 0.9074626865671642,
      "grad_norm": 0.2552385628223419,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.4589,
      "step": 19
    },
    {
      "epoch": 0.9552238805970149,
      "grad_norm": 0.2948434054851532,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.3964,
      "step": 20
    },
    {
      "epoch": 1.026865671641791,
      "grad_norm": 0.2875458896160126,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.7961,
      "step": 21
    },
    {
      "epoch": 1.0746268656716418,
      "grad_norm": 0.16467946767807007,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.4402,
      "step": 22
    },
    {
      "epoch": 1.1223880597014926,
      "grad_norm": 0.19330933690071106,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.403,
      "step": 23
    },
    {
      "epoch": 1.1701492537313434,
      "grad_norm": 0.21502898633480072,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.4137,
      "step": 24
    },
    {
      "epoch": 1.217910447761194,
      "grad_norm": 0.2619268298149109,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.4207,
      "step": 25
    },
    {
      "epoch": 1.217910447761194,
      "eval_loss": 0.4253615736961365,
      "eval_runtime": 1.6379,
      "eval_samples_per_second": 86.087,
      "eval_steps_per_second": 10.99,
      "step": 25
    },
    {
      "epoch": 1.2656716417910447,
      "grad_norm": 0.18392308056354523,
      "learning_rate": 5e-05,
      "loss": 0.3783,
      "step": 26
    },
    {
      "epoch": 1.3134328358208955,
      "grad_norm": 0.17759908735752106,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 0.4182,
      "step": 27
    },
    {
      "epoch": 1.3611940298507463,
      "grad_norm": 0.19861653447151184,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.4159,
      "step": 28
    },
    {
      "epoch": 1.408955223880597,
      "grad_norm": 0.21638356149196625,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.3822,
      "step": 29
    },
    {
      "epoch": 1.4567164179104477,
      "grad_norm": 0.2728606164455414,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.3745,
      "step": 30
    },
    {
      "epoch": 1.5044776119402985,
      "grad_norm": 0.1896788477897644,
      "learning_rate": 3.392802673484193e-05,
      "loss": 0.3724,
      "step": 31
    },
    {
      "epoch": 1.5522388059701493,
      "grad_norm": 0.19130320847034454,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.4189,
      "step": 32
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.2291479855775833,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 0.4087,
      "step": 33
    },
    {
      "epoch": 1.6477611940298509,
      "grad_norm": 0.24589583277702332,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.4007,
      "step": 34
    },
    {
      "epoch": 1.6955223880597015,
      "grad_norm": 0.25085797905921936,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.3735,
      "step": 35
    },
    {
      "epoch": 1.7432835820895523,
      "grad_norm": 0.2219715267419815,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.3978,
      "step": 36
    },
    {
      "epoch": 1.7910447761194028,
      "grad_norm": 0.1881018429994583,
      "learning_rate": 1.703270924499656e-05,
      "loss": 0.3952,
      "step": 37
    },
    {
      "epoch": 1.8388059701492536,
      "grad_norm": 0.21645773947238922,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.4167,
      "step": 38
    },
    {
      "epoch": 1.8865671641791044,
      "grad_norm": 0.2337845265865326,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 0.377,
      "step": 39
    },
    {
      "epoch": 1.9343283582089552,
      "grad_norm": 0.2754746079444885,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.368,
      "step": 40
    },
    {
      "epoch": 2.005970149253731,
      "grad_norm": 0.30742526054382324,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.5339,
      "step": 41
    },
    {
      "epoch": 2.053731343283582,
      "grad_norm": 0.1772758960723877,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.3891,
      "step": 42
    },
    {
      "epoch": 2.1014925373134328,
      "grad_norm": 0.19144101440906525,
      "learning_rate": 5.156362923365588e-06,
      "loss": 0.3792,
      "step": 43
    },
    {
      "epoch": 2.1492537313432836,
      "grad_norm": 0.2184714525938034,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.3801,
      "step": 44
    },
    {
      "epoch": 2.1970149253731344,
      "grad_norm": 0.25839197635650635,
      "learning_rate": 2.653493525244721e-06,
      "loss": 0.384,
      "step": 45
    },
    {
      "epoch": 2.244776119402985,
      "grad_norm": 0.26673170924186707,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.3292,
      "step": 46
    },
    {
      "epoch": 2.292537313432836,
      "grad_norm": 0.18285243213176727,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.4068,
      "step": 47
    },
    {
      "epoch": 2.3402985074626868,
      "grad_norm": 0.20161080360412598,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.3849,
      "step": 48
    },
    {
      "epoch": 2.388059701492537,
      "grad_norm": 0.21239733695983887,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 0.3788,
      "step": 49
    },
    {
      "epoch": 2.435820895522388,
      "grad_norm": 0.23920461535453796,
      "learning_rate": 0.0,
      "loss": 0.3511,
      "step": 50
    },
    {
      "epoch": 2.435820895522388,
      "eval_loss": 0.4024839401245117,
      "eval_runtime": 1.638,
      "eval_samples_per_second": 86.08,
      "eval_steps_per_second": 10.989,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.059536353886208e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}